© 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. 0-CLT-HP
    7. 94218
    Prev
    Next
    INDEX
    Explanations

    en

    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
    en
    -2.06
    es
    -1.59
    ds
    -1.03
    er
    -0.97
    in
    -0.92
    u
    -0.87
    EN
    -0.85
    y
    -0.84
    des
    -0.82
    as
    -0.82
    POSITIVE LOGITS
     myſelf
    1.48
     Efq
    1.38
    ^(@)
    1.32
     itſelf
    1.30
     themſelves
    1.23
    TypedDataSet
    1.23
    DockStyle
    1.22
     himſelf
    1.21
     Monfieur
    1.21
    ſelves
    1.18
    Activations Density 0.095%

    No Known Activations