© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 14231
    Prev
    Next
    INDEX
    Explanations

    the

    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
    \{\\
    -0.61
    .*")]
    -0.60
    ')).
    -0.60
    ')):
    -0.57
     façon
    -0.53
    ']).
    -0.52
     ""));
    -0.52
    --}}
    -0.52
    '])->
    -0.52
    hard
    -0.52
    POSITIVE LOGITS
    transQ
    0.62
    twimg
    0.60
    HasColumnType
    0.57
    MessageOf
    0.54
    niająca
    0.51
    localctx
    0.51
    figer
    0.51
    warted
    0.51
    BACK
    0.50
    PostExecute
    0.50
    Activations Density 0.028%

    No Known Activations