© 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. 5-CLT-HP
    7. 96080
    Prev
    Next
    INDEX
    Explanations

    joining events or groups

    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
    ization
    -0.47
    .
    -0.43
    İstinadlar
    -0.40
    izations
    -0.39
    atrici
    -0.38
     citer
    -0.38
     (
    -0.37
    قال
    -0.36
    -,
    -0.36
    ’
    -0.35
    POSITIVE LOGITS
     CURIAM
    0.84
     صوتيه
    0.82
    Personendaten
    0.70
    醐
    0.70
    \{\\
    0.68
    zędu
    0.68
     parseFrom
    0.65
    dillera
    0.64
     незавершена
    0.63
     مرئيه
    0.63
    Activations Density 0.005%

    No Known Activations