© 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. 1-CLT-HP
    7. 14461
    Prev
    Next
    INDEX
    Explanations

    or

    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
    Personendaten
    -0.68
    copg
    -0.67
    +#+#
    -0.66
     fieldNum
    -0.66
    TagMode
    -0.66
    numerusform
    -0.63
    ագրություններ
    -0.63
    InputBorder
    -0.61
     Normdatei
    -0.61
    AutoScaleMode
    -0.60
    POSITIVE LOGITS
     the
    0.71
     an
    0.66
     their
    0.62
     some
    0.61
     a
    0.60
    yntaxException
    0.60
    s
    0.59
     any
    0.57
     its
    0.56
     ſay
    0.56
    Activations Density 0.401%

    No Known Activations