© 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. 4-CLT-HP
    7. 3440
    Prev
    Next
    INDEX
    Explanations

    alternatives

    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
    ResumeLayout
    -0.56
    '])->
    -0.56
     Bioaccumulative
    -0.55
    Bands
    -0.52
     utafitiHapana
    -0.50
    Pairs
    -0.49
    تقاوى
    -0.48
    Lines
    -0.47
    ']));
    -0.47
     of
    -0.46
    POSITIVE LOGITS
     side
    0.90
     way
    0.80
     part
    0.71
     CreateTagHelper
    0.68
     factor
    0.59
    Datuak
    0.59
    enterOuterAlt
    0.56
     WAY
    0.56
     force
    0.55
     SIDE
    0.54
    Activations Density 0.005%

    No Known Activations