© 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. 14477
    Prev
    Next
    INDEX
    Explanations

    body

    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
     nargin
    -0.53
    createServer
    -0.52
    __*/
    -0.51
    PyTuple
    -0.48
    stateParams
    -0.47
    waters
    -0.47
    PhysRevLett
    -0.47
     nakalista
    -0.46
     memoized
    -0.45
    ILITIES
    -0.45
    POSITIVE LOGITS
     defaultstate
    0.54
    yntaxException
    0.54
    vité
    0.51
    znym
    0.51
    urgy
    0.50
     GenerationType
    0.50
    izarse
    0.49
     Italijanski
    0.48
     Trick
    0.48
    XmlAccessorType
    0.47
    Activations Density 0.054%

    No Known Activations