© 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. 5062
    Prev
    Next
    INDEX
    Explanations

    (['

    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
    .*")]
    -0.93
    DockStyle
    -0.88
    TypedDataSet
    -0.82
    AsUp
    -0.81
     getItemId
    -0.80
     venons
    -0.79
    LookAnd
    -0.79
    SequentialGroup
    -0.79
    requestCode
    -0.77
     extérieurs
    -0.76
    POSITIVE LOGITS
     state
    0.42
     now
    0.41
     word
    0.39
     rés
    0.38
     per
    0.38
     single
    0.37
     we
    0.37
     open
    0.37
     our
    0.37
     Open
    0.36
    Activations Density 0.001%

    No Known Activations