© 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. 15776
    Prev
    Next
    INDEX
    Explanations

    locations and names

    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
     Rafael
    -1.62
    Rafael
    -1.38
     rafael
    -0.80
    IsMutable
    -0.77
     Rafa
    -0.77
     مرئيه
    -0.75
    #+#
    -0.74
    Rafa
    -0.66
    uds
    -0.64
    XmlAccessType
    -0.63
    POSITIVE LOGITS
    WarningLevel
    0.49
    ScopeManager
    0.49
    hael
    0.48
    droj
    0.46
    leon
    0.44
    uto
    0.43
     suéter
    0.42
     nonatomic
    0.41
    ulen
    0.40
    yl
    0.40
    Activations Density 0.028%

    No Known Activations