© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1017
    Prev
    Next
    INDEX
    Explanations

    Technical web content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bibliograf
    -0.49
    {}'.
    -0.44
    '):
    -0.42
    ToAction
    -0.41
     tot
    -0.40
    asına
    -0.40
    umą
    -0.39
    }}}$
    -0.39
    ]--;
    -0.39
    
    -0.39
    POSITIVE LOGITS
     propOrder
    0.82
    twimg
    0.77
     CreateTagHelper
    0.76
     ProtoMessage
    0.71
     BufferedWriter
    0.69
    новниш
    0.69
    OGND
    0.69
    PageContext
    0.68
    WriteBarrier
    0.66
     calendriers
    0.66
    Activations Density 0.016%

    No Known Activations