© 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. 10234
    Prev
    Next
    INDEX
    Explanations

    line

    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
     line
    -0.47
    tagHelper
    -0.44
    ments
    -0.44
    linien
    -0.44
    ms
    -0.44
    lo
    -0.43
    PERTY
    -0.43
    ีย์
    -0.43
    Line
    -0.43
    ]-->
    -0.43
    POSITIVE LOGITS
     صوتيه
    0.77
     nahilalakip
    0.74
     SwitchCompat
    0.71
    IVEREF
    0.66
     Roskov
    0.63
    UnknownFields
    0.63
    IntoConstraints
    0.63
    ViewFeatures
    0.61
    officer
    0.58
     povezave
    0.58
    Activations Density 0.009%

    No Known Activations