© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74572
    Prev
    Next
    INDEX
    Explanations

    scientific publications

    np_max-act-logits · 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
     '\\;'
    -0.68
    LookAnd
    -0.61
    })`
    -0.60
     متعلقه
    -0.57
     deleteUser
    -0.56
    onAttach
    -0.56
     يتيمه
    -0.54
    oucí
    -0.54
    цезда
    -0.54
    tanleria
    -0.54
    POSITIVE LOGITS
     national
    0.57
    Спољашње
    0.54
    new
    0.53
    national
    0.53
     new
    0.52
    COUVER
    0.51
     National
    0.51
    National
    0.50
    VELAND
    0.49
    chemistry
    0.49
    Activations Density 0.000%

    No Known Activations