© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12318
    Prev
    Next
    INDEX
    Explanations

    official matters

    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
    enterOuterAlt
    -0.78
    Geplaatst
    -0.78
    ]")]
    -0.69
     HasFactory
    -0.68
    Autoritní
    -0.66
    CloseOperation
    -0.66
    पया
    -0.65
     wikipagina
    -0.64
    WaitGroup
    -0.63
    __(/*!
    -0.62
    POSITIVE LOGITS
    tier
    0.50
    baldi
    0.44
     Jones
    0.42
    odacty
    0.42
    lic
    0.42
    cratic
    0.42
     Tavares
    0.41
    pter
    0.41
     Lazarus
    0.41
    leon
    0.40
    Activations Density 0.026%

    No Known Activations