© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4912
    Prev
    Next
    INDEX
    Explanations

    of

    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
     it
    -0.68
     not
    -0.56
     this
    -0.55
     no
    -0.52
     the
    -0.51
     sachant
    -0.51
     knowing
    -0.48
    it
    -0.48
    not
    -0.48
    how
    -0.47
    POSITIVE LOGITS
    TypedDataSet
    0.91
     Waray
    0.71
    complexContent
    0.69
     nakalista
    0.66
    rungsseite
    0.65
     виправивши
    0.65
    BufferException
    0.63
    StreetMap
    0.63
    saurus
    0.60
    ")));
    0.60
    Activations Density 0.002%

    No Known Activations