© 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. 206
    Prev
    Next
    INDEX
    Explanations

    descriptive qualities

    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
    basicConfig
    -0.59
    Referencie
    -0.57
    findpost
    -0.55
    ⓧ
    -0.54
    出版年
    -0.54
    __':
    -0.54
     createSlice
    -0.53
    ComponentScan
    -0.53
     digitais
    -0.51
    __":
    -0.50
    POSITIVE LOGITS
    ]='\
    0.54
     calldata
    0.50
    verture
    0.46
    tées
    0.46
     gravity
    0.46
    rophore
    0.46
    ʲ
    0.45
    freies
    0.44
    ussis
    0.44
    Keterangan
    0.44
    Activations Density 0.001%

    No Known Activations