© 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. 1-CLT-HP
    7. 13028
    Prev
    Next
    INDEX
    Explanations

    frame

    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
     Frame
    -2.03
    Frame
    -2.02
     frame
    -1.99
    frame
    -1.89
     FRAME
    -1.80
     frames
    -1.74
     Frames
    -1.70
    FRAME
    -1.63
    Frames
    -1.51
    frames
    -1.48
    POSITIVE LOGITS
    ctory
    0.60
    ScopeManager
    0.57
     Cowley
    0.53
     voltam
    0.52
    etcode
    0.52
    oglobin
    0.52
    quium
    0.51
    mius
    0.51
    GOD
    0.50
    vowel
    0.50
    Activations Density 0.047%

    No Known Activations