© 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. 4-CLT-HP
    7. 957
    Prev
    Next
    INDEX
    Explanations

    Research/news documents

    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
    ousal
    -0.47
     Ook
    -0.46
    itude
    -0.44
    Stell
    -0.42
     occasion
    -0.42
     Nub
    -0.42
     occasions
    -0.42
    ish
    -0.41
    Clik
    -0.41
     MBS
    -0.41
    POSITIVE LOGITS
    oredCriteria
    0.77
    TagMode
    0.75
    DockStyle
    0.74
    fjspx
    0.65
    arrings
    0.63
    principalColumn
    0.61
     unknownFields
    0.59
    writeField
    0.58
    FormTagHelper
    0.57
    InvalidProtocol
    0.57
    Activations Density 0.022%

    No Known Activations