© 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. 97516
    Prev
    Next
    INDEX
    Explanations

    values and goals

    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
    ^*)
    -0.65
    AxisAlignment
    -0.62
     noDo
    -0.61
    ]--;
    -0.60
    makeConstraints
    -0.60
    ]++;
    -0.59
     beginnetje
    -0.58
    esterday
    -0.56
     EnglishChoose
    -0.56
     doInBackground
    -0.56
    POSITIVE LOGITS
    例文
    0.52
     AssemblyVersion
    0.52
    Cyfeiriadau
    0.47
    IDENTIAL
    0.47
     cucchiai
    0.47
    n
    0.46
    ন্ত
    0.46
     selectivity
    0.45
     of
    0.44
     publiques
    0.44
    Activations Density 0.011%

    No Known Activations