© 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. 5-CLT-HP
    7. 98281
    Prev
    Next
    INDEX
    Explanations

    Overcoming challenges

    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
    <bos>
    -0.77
     resourceCulture
    -0.54
    AnchorStyles
    -0.53
     bords
    -0.52
    ])->
    -0.48
    PreExecute
    -0.48
    principalTable
    -0.47
    onViewCreated
    -0.46
    UnifiedTopology
    -0.44
    MockBean
    -0.44
    POSITIVE LOGITS
    Демографія
    0.72
     
    0.69
    __*/
    0.68
    cèse
    0.60
    COUVER
    0.59
    NECTION
    0.57
     EnglishChoose
    0.56
    الدراسه
    0.56
    PRWEB
    0.55
    PhysRevD
    0.55
    Activations Density 0.004%

    No Known Activations