© 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. 92093
    Prev
    Next
    INDEX
    Explanations

    Information sources

    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
    ChildScrollView
    -0.53
    setVerticalGroup
    -0.52
    MENAFN
    -0.51
    rungsseite
    -0.51
    __*/
    -0.46
     protoimpl
    -0.45
     pinulongan
    -0.40
     Mérimée
    -0.40
    TabIndex
    -0.38
    bitField
    -0.38
    POSITIVE LOGITS
     HasFactory
    0.77
    сылкі
    0.60
    endpush
    0.60
    IndentedString
    0.60
    YMS
    0.60
    Vanjske
    0.58
    Viki
    0.58
    WriteBarrier
    0.58
     Wonderland
    0.57
    encodeWith
    0.56
    Activations Density 0.003%

    No Known Activations