© 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. 4768
    Prev
    Next
    INDEX
    Explanations

    v

    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
     and
    -0.54
    ActionCreators
    -0.52
     but
    -0.52
     or
    -0.51
    .
    -0.50
     due
    -0.49
     of
    -0.45
     surla
    -0.44
     over
    -0.44
     by
    -0.44
    POSITIVE LOGITS
     Philist
    0.79
    GEBURTSDATUM
    0.73
     Administrativna
    0.73
    =$?
    0.73
    ArgsConstructor
    0.71
    Cyfeiriadau
    0.69
    yntaxException
    0.68
    Abitanti
    0.68
    󠁢
    0.66
     tattoos
    0.66
    Activations Density 0.000%

    No Known Activations