© 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. 20-CLT-HP
    7. 75325
    Prev
    Next
    INDEX
    Explanations

    code and files

    np_max-act-logits · 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
    WireFormatLite
    -0.72
    djangoproject
    -0.70
    mapStateToProps
    -0.66
    '][]
    -0.66
     Milky
    -0.65
    }$​
    -0.65
    =?";
    -0.64
     EconPapers
    -0.63
    ⎓
    -0.62
     \%$\\
    -0.61
    POSITIVE LOGITS
     broad
    0.42
    WebMethod
    0.41
     exteriores
    0.37
     natural
    0.35
     saites
    0.33
     BROAD
    0.31
    plink
    0.31
    nå
    0.31
    ėjimas
    0.30
     nice
    0.30
    Activations Density 0.000%

    No Known Activations