© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45803
    Prev
    Next
    INDEX
    Explanations

    minimal

    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
    tvguidetime
    -0.71
    CopyWith
    -0.57
     Drapeau
    -0.56
    })));
    -0.56
    farwyddwr
    -0.52
    horabuena
    -0.52
     సౌకర్య
    -0.51
    iconque
    -0.50
    Izvori
    -0.50
     guère
    -0.50
    POSITIVE LOGITS
    SourceChecksum
    0.66
    出版年
    0.49
     to
    0.49
     AssemblyVersion
    0.47
    agd
    0.46
     محفوظة
    0.46
     effect
    0.46
    putstr
    0.45
     المكتبه
    0.45
     lakini
    0.45
    Activations Density 0.008%

    No Known Activations