© 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. 94150
    Prev
    Next
    INDEX
    Explanations

    name

    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
     name
    -1.03
     names
    -1.03
    name
    -0.93
    Name
    -0.88
    names
    -0.84
     Name
    -0.82
     Names
    -0.80
    Names
    -0.76
     Audiodateien
    -0.74
    NAME
    -0.72
    POSITIVE LOGITS
     of
    0.79
     Himo
    0.66
    renos
    0.47
     posé
    0.44
     Mundi
    0.44
     obce
    0.44
    setUrl
    0.43
    __(/*!
    0.43
    喱
    0.42
     của
    0.42
    Activations Density 0.035%

    No Known Activations