© 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. 5-CLT-HP
    7. 96932
    Prev
    Next
    INDEX
    Explanations

    digits

    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
     tartalomajánló
    -0.91
     betweenstory
    -0.90
     виправивши
    -0.78
     magnético
    -0.76
     disambiguazione
    -0.73
    ^(@)
    -0.73
    Filmografia
    -0.72
    airobi
    -0.72
    >*/
    -0.72
    HostException
    -0.72
    POSITIVE LOGITS
     suicidio
    0.35
    d
    0.34
    MetaObject
    0.33
    c
    0.33
    чи
    0.31
     tito
    0.31
    dele
    0.31
    endorff
    0.30
    casa
    0.30
    CodeAttribute
    0.29
    Activations Density 0.006%

    No Known Activations