Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73868
    Prev
    Next
    INDEX
    Explanations

    code context

    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
    MemoryWarning
    -0.86
    SequentialGroup
    -0.74
    ThroughAttribute
    -0.73
     mergeFrom
    -0.69
     للاسماء
    -0.69
     ModelExpression
    -0.68
     Keepers
    -0.67
    Koordinaten
    -0.66
     NUKAT
    -0.65
    Geplaatst
    -0.65
    POSITIVE LOGITS
     and
    0.45
    aculture
    0.44
    HostException
    0.42
     psycopg
    0.41
     AttributeSet
    0.41
    ClientRect
    0.41
    now
    0.40
    -
    0.40
    AttributeSet
    0.40
    storm
    0.40
    Activations Density 0.007%

    No Known Activations