© 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. 9403
    Prev
    Next
    INDEX
    Explanations

    length

    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
    Referències
    -0.47
    __*/
    -0.44
     continúas
    -0.43
    Примітки
    -0.39
     écrite
    -0.37
    signature
    -0.36
     signature
    -0.36
    比
    -0.36
    мпа
    -0.36
    nende
    -0.35
    POSITIVE LOGITS
    InitVars
    0.74
    Autoritní
    0.66
    yarnpkg
    0.63
     neonatal
    0.63
    EndContext
    0.60
    InstanceState
    0.58
    thood
    0.58
    ochrome
    0.57
    ocarditis
    0.57
     Galactic
    0.57
    Activations Density 0.036%

    No Known Activations