© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-RES-MATRYOSHKA-DC
    4. 2128
    Prev
    Next
    INDEX
    Explanations

    what appears to be random numerical and special character sequences

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.72
     }}}
    -0.56
    ]]);
    -0.56
    )),
    
    -0.55
    ]));
    
    -0.54
    \}^{
    -0.53
    ()]);
    -0.53
    ']?>
    -0.53
    )]);
    -0.53
    ]),
    
    -0.52
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.69
    WriteTagHelper
    0.69
    Bioaccumulative
    0.59
    intenance
    0.59
    BeginInit
    0.58
     isInitialized
    0.57
    DockStyle
    0.56
     sort
    0.56
    ennium
    0.55
    principalColumn
    0.55
    Activations Density 0.525%

    No Known Activations