© 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. 0-CLT-HP
    7. 97740
    Prev
    Next
    INDEX
    Explanations

    continues

    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
     continues
    -0.75
     autorytatywna
    -0.57
    Composable
    -0.54
    än
    -0.53
    χ
    -0.50
     Kam
    -0.46
    etal
    -0.45
     continued
    -0.44
    uben
    -0.44
     starter
    -0.43
    POSITIVE LOGITS
    +#+#
    0.91
    +:+
    0.70
    kään
    0.62
    yntaxException
    0.61
    ніципа
    0.60
    évaluateur
    0.58
    +#+
    0.57
    thique
    0.56
     supervise
    0.55
    zzleHttp
    0.55
    Activations Density 0.115%

    No Known Activations