© 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. 5-CLT-HP
    7. 4912
    Prev
    Next
    INDEX
    Explanations

    collective

    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
    DoubleQuotes
    -0.74
     propOrder
    -0.71
    UnknownFields
    -0.65
     stället
    -0.63
    WriteAttribute
    -0.60
    onAttach
    -0.59
     hinweg
    -0.58
    GeoNames
    -0.58
    whole
    -0.57
     prépar
    -0.56
    POSITIVE LOGITS
    LookAnd
    0.50
    醐
    0.49
    ioneta
    0.48
    otent
    0.47
    taines
    0.47
     addiction
    0.47
    MAH
    0.46
    lieg
    0.46
    ungsver
    0.46
    illoma
    0.45
    Activations Density 0.002%

    No Known Activations