© 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. 12113
    Prev
    Next
    INDEX
    Explanations

    Rother

    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
     Rother
    -0.85
    onor
    -0.66
    Diweddarwch
    -0.62
    findpost
    -0.60
    wark
    -0.53
    WEBPACK
    -0.52
    sidemargin
    -0.51
    dafx
    -0.50
    AutoScaleMode
    -0.50
    matchCondition
    -0.48
    POSITIVE LOGITS
    ham
    0.59
     viewDidLoad
    0.55
    hip
    0.51
     Offisielt
    0.51
    mel
    0.50
     الحره
    0.49
    VolleyError
    0.49
    psum
    0.48
     cuillère
    0.47
     Photographie
    0.47
    Activations Density 0.005%

    No Known Activations