© 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. 15146
    Prev
    Next
    INDEX
    Explanations

    competition

    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
    IsContent
    -0.63
    MessageOf
    -0.61
    Personensuche
    -0.61
     كومونز
    -0.61
    HostException
    -0.58
    таратура
    -0.58
    UnusedPrivate
    -0.58
    DockStyle
    -0.56
    LoggerFactory
    -0.56
    GenerationType
    -0.56
    POSITIVE LOGITS
    PyExc
    0.48
     currentState
    0.46
    тивной
    0.45
     claims
    0.45
     claim
    0.44
     claiming
    0.44
    μεν
    0.44
     endforeach
    0.44
     removeFrom
    0.43
     Artik
    0.43
    Activations Density 0.008%

    No Known Activations