© 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. 1-CLT-HP
    4. 45714
    Prev
    Next
    INDEX
    Explanations

    harp

    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
     Harp
    -1.23
     harp
    -0.99
    Harp
    -0.91
     drum
    -0.85
     Drum
    -0.83
    Drum
    -0.74
    drum
    -0.65
    harp
    -0.58
     DRUM
    -0.57
     tambor
    -0.52
    POSITIVE LOGITS
     kaarangay
    0.91
     betweenstory
    0.89
    AndEndTag
    0.82
    httphttps
    0.81
     autorytatywna
    0.77
     defaultstate
    0.74
    Autoritní
    0.74
    GEBURTSDATUM
    0.74
     HasFactory
    0.73
     ModelExpression
    0.71
    Activations Density 0.026%

    No Known Activations